We examine the application of data-driven paraphrasing to natural language understanding. We leverage bilingual parallel corpora to extract a large collection of syntactic paraphrase pairs, and introduce an adaptation scheme that allows us to tackle a variety of text transformation tasks via paraphrasing. We evaluate our system on the sentence compression task. Further, we use distributional si...

Paraphrasing is an important aspect of language competence; however, EFL learners have long had difficulty paraphrasing in their writing owing to their limited language proficiency. Therefore, automatic paraphrase suggestion systems can be useful for writers. In this paper, we present PREFER 1 , a paraphrase reference tool for helping language learners improve their writing skills. In this pape...

The lack of Indonesian students performing their abilities in L1 paraphrasing becomes the primary reason they are labeled as persistent plagiarizers. Students, context and circumstances, need to broaden perspectives regarding how document sources, using them original papers support defend arguments. Literacy should be developed sustainably order for might critically think state things with evid...

Abstract Recently, natural language processing researches have focused on data or processing techniques for paraphrasing. Unfortunately, however, we have little data for paraphrasing. There are some research reports on collecting synonymous expressions with parallel corpus, though no suitable corpus for collecting a set of paraphrases is yet available. Therefore, we obtain a few variations of e...

A time-sharing study used shadowing and interpretation/paraphrasing tasks to evaluate lateralization in professional interpreters individually matched to bilingual and monolingual controls. A two-step multivariate general linear model procedure was used to determine lateralized effects and extent of disruption produced by the tasks. Results revealed the monolingual group to be left lateralized ...

Ideally a metric evaluating an abstract system summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a humanwritten reference summary. Most of the previous approaches relied upon word or syntactic sub-sequence overlap to evaluate system-generated summaries. Such metrics cannot evaluate the summary at semantic ...

The goal of the information analysis process is to derive the information grammar which describes the communication language within some application domain. This process involves both domain experts and system analysts. Since good communication between these two partners is essential, a proper common language should be chosen. Natural language seems to be a good candidate for this purpose. Two ...

We present a method for improving machine translation (MT) evaluation by targeted paraphrasing of reference sentences. For this purpose, we employ MT systems themselves and adapt them for translating within a single language. We describe this attempt on two types of MT systems – phrase-based and rule-based. Initially, we experiment with the freely available SMT system Moses. We create translati...